Leveraging Previous Steps: A Training-free Fast Solver for Flow Diffusion

• URL: http://arxiv.org/abs/2411.07627v1
• Date: Tue, 12 Nov 2024 08:17:15 GMT
• Title: Leveraging Previous Steps: A Training-free Fast Solver for Flow Diffusion
• Authors: Kaiyu Song, Hanjiang Lai,
• Abstract summary: Flow diffusion models (FDMs) have recently shown potential in generation tasks due to the high generation quality. The current ordinary differential equation (ODE) solver for FDMs, e.g., the solver, still suffers from slow generation. We propose a novel training-free flow-solver to reduce NFE while maintaining high-quality generation.
• Score: 7.3604864243987365
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Flow diffusion models (FDMs) have recently shown potential in generation tasks due to the high generation quality. However, the current ordinary differential equation (ODE) solver for FDMs, e.g., the Euler solver, still suffers from slow generation since ODE solvers need many number function evaluations (NFE) to keep high-quality generation. In this paper, we propose a novel training-free flow-solver to reduce NFE while maintaining high-quality generation. The key insight for the flow-solver is to leverage the previous steps to reduce the NFE, where a cache is created to reuse these results from the previous steps. Specifically, the Taylor expansion is first used to approximate the ODE. To calculate the high-order derivatives of Taylor expansion, the flow-solver proposes to use the previous steps and a polynomial interpolation to approximate it, where the number of orders we could approximate equals the number of previous steps we cached. We also prove that the flow-solver has a more minor approximation error and faster generation speed. Experimental results on the CIFAR-10, CelebA-HQ, LSUN-Bedroom, LSUN-Church, ImageNet, and real text-to-image generation prove the efficiency of the flow-solver. Specifically, the flow-solver improves the FID-30K from 13.79 to 6.75, from 46.64 to 19.49 with $\text{NFE}=10$ on CIFAR-10 and LSUN-Church, respectively.

Related papers

• ProReflow: Progressive Reflow with Decomposed Velocity [52.249464542399636]
  Flow matching aims to reflow the diffusion process of diffusion models into a straight line for a few-step and even one-step generation. We introduce progressive reflow, which progressively reflows the diffusion models in local timesteps until the whole diffusion progresses. We also introduce aligned v-prediction, which highlights the importance of direction matching in flow matching over magnitude matching.
  arXiv  Detail & Related papers  (2025-03-05T04:50:53Z)
• S4S: Solving for a Diffusion Model Solver [52.99341671532249]
  Diffusion models (DMs) create samples from a data distribution by starting from random noise and solving a reverse-time ordinary differential equation (ODE) We propose a new method that learns a good solver for the DM, which we call Solving for the Solver (S4S) In all settings, S4S uniformly improves the sample quality relative to traditional ODE solvers.
  arXiv  Detail & Related papers  (2025-02-24T18:55:54Z)
• Rectified Diffusion: Straightness Is Not Your Need in Rectified Flow [65.51671121528858]
  Diffusion models have greatly improved visual generation but are hindered by slow generation speed due to the computationally intensive nature of solving generative ODEs. Rectified flow, a widely recognized solution, improves generation speed by straightening the ODE path. We propose Rectified Diffusion, which generalizes the design space and application scope of rectification to encompass the broader category of diffusion models.
  arXiv  Detail & Related papers  (2024-10-09T17:43:38Z)
• PFDiff: Training-free Acceleration of Diffusion Models through the Gradient Guidance of Past and Future [4.595421654683656]
  Diffusion Probabilistic Models (DPMs) have shown remarkable potential in image generation, but their sampling efficiency is hindered by the need for numerous denoising steps. We propose PFDiff, a novel training-free and timestep-skipping strategy, which enables existing fast ODE solvers to operate with fewer NFE.
  arXiv  Detail & Related papers  (2024-08-16T16:12:44Z)
• Consistency Flow Matching: Defining Straight Flows with Velocity Consistency [97.28511135503176]
  We introduce Consistency Flow Matching (Consistency-FM), a novel FM method that explicitly enforces self-consistency in the velocity field. Preliminary experiments demonstrate that our Consistency-FM significantly improves training efficiency by converging 4.4x faster than consistency models.
  arXiv  Detail & Related papers  (2024-07-02T16:15:37Z)
• Improving the Training of Rectified Flows [14.652876697052156]
  Diffusion models have shown great promise for image and video generation, but sampling from state-of-the-art models requires expensive numerical integration of a generative ODE. One approach for tackling this problem is rectified flows, which iteratively learn smooth ODE paths that are less susceptible to truncation error. We propose improved techniques for training rectified flows, allowing them to compete with emphknowledge distillation methods even in the low NFE setting. Our improved rectified flow outperforms the state-of-the-art distillation methods such as consistency distillation and progressive distillation in both one-step and two
  arXiv  Detail & Related papers  (2024-05-30T17:56:04Z)
• Bridging Discrete and Backpropagation: Straight-Through and Beyond [62.46558842476455]
  We propose a novel approach to approximate the gradient of parameters involved in generating discrete latent variables. We propose ReinMax, which achieves second-order accuracy by integrating Heun's method, a second-order numerical method for solving ODEs.
  arXiv  Detail & Related papers  (2023-04-17T20:59:49Z)
• GENIE: Higher-Order Denoising Diffusion Solvers [19.79516951865819]
  Denoising diffusion models (DDMs) have emerged as a powerful class of generative models. A forward diffusion process slowly perturbs the data, while a deep model learns to gradually denoise. Solving the differential equation (DE) defined by the learnt model requires slow iterative solvers for high-quality generation. We propose a novel higher-order solver that significantly accelerates synthesis.
  arXiv  Detail & Related papers  (2022-10-11T14:18:28Z)
• Neural Basis Functions for Accelerating Solutions to High Mach Euler Equations [63.8376359764052]
  We propose an approach to solving partial differential equations (PDEs) using a set of neural networks. We regress a set of neural networks onto a reduced order Proper Orthogonal Decomposition (POD) basis. These networks are then used in combination with a branch network that ingests the parameters of the prescribed PDE to compute a reduced order approximation to the PDE.
  arXiv  Detail & Related papers  (2022-08-02T18:27:13Z)
• Deep Equilibrium Optical Flow Estimation [80.80992684796566]
  Recent state-of-the-art (SOTA) optical flow models use finite-step recurrent update operations to emulate traditional algorithms. These RNNs impose large computation and memory overheads, and are not directly trained to model such stable estimation. We propose deep equilibrium (DEQ) flow estimators, an approach that directly solves for the flow as the infinite-level fixed point of an implicit layer.
  arXiv  Detail & Related papers  (2022-04-18T17:53:44Z)
• GMFlow: Learning Optical Flow via Global Matching [124.57850500778277]
  We propose a GMFlow framework for learning optical flow estimation. It consists of three main components: a customized Transformer for feature enhancement, a correlation and softmax layer for global feature matching, and a self-attention layer for flow propagation. Our new framework outperforms 32-iteration RAFT's performance on the challenging Sintel benchmark.
  arXiv  Detail & Related papers  (2021-11-26T18:59:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.